SPARSITY-AWARE ORTHOGONAL INITIALIZATION OF MULTILAYER PERCEPTRONS AND CONVOLUTIONAL NEURAL NETWORKS

ESGUERRA, KIARA SANDEL (2023) SPARSITY-AWARE ORTHOGONAL INITIALIZATION OF MULTILAYER PERCEPTRONS AND CONVOLUTIONAL NEURAL NETWORKS. Masters thesis, Universiti Teknologi PETRONAS.

Full text not available from this repository.

Abstract

Deep neural networks have achieved impressive pattern recognition and generative abilities on complex tasks by developing larger and deeper models, which are increasingly costly to train and implement.

Item Type:	Thesis (Masters)
Subjects:	T Technology > TK Electrical engineering. Electronics Nuclear engineering
Departments / MOR / COE:	Engineering > Electrical and Electronic
Depositing User:	Mr Ahmad Suhairi Mohamed Lazim
Date Deposited:	05 Jun 2024 06:30
Last Modified:	05 Jun 2024 06:30
URI:	http://utpedia.utp.edu.my/id/eprint/27045

Actions (login required)

: View Item